ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts
This work provides empirical guidance for designing vision MoE models, addressing a domain-specific problem in computer vision, but it is incremental as it builds on existing MoE and ViT concepts.
The authors tackled the challenge of integrating Mixture-of-Experts (MoE) into Vision Transformers (ViT) for image classification and semantic segmentation, finding that performance is sensitive to MoE layer configuration and introducing a shared expert to stabilize the model, which improved efficiency without accuracy loss.
Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multiple domains. In this paper, we integrate the MoE structure into the classic Vision Transformer (ViT), naming it ViMoE, and explore the potential of applying MoE to vision through a comprehensive study on image classification and semantic segmentation. However, we observe that the performance is sensitive to the configuration of MoE layers, making it challenging to obtain optimal results without careful design. The underlying cause is that inappropriate MoE layers lead to unreliable routing and hinder experts from effectively acquiring helpful information. To address this, we introduce a shared expert to learn and capture common knowledge, serving as an effective way to construct stable ViMoE. Furthermore, we demonstrate how to analyze expert routing behavior, revealing which MoE layers are capable of specializing in handling specific information and which are not. This provides guidance for retaining the critical layers while removing redundancies, thereby advancing ViMoE to be more efficient without sacrificing accuracy. We aspire for this work to offer new insights into the design of vision MoE models and provide valuable empirical guidance for future research.